我有以下样本数据，使用回归算法预测时间。我也使用了lightgbm和xgboost训练模型，但是我得到的预测结果非常差，而且预测结果是负值。我不确定我哪里做错了，谢谢
size channels time3 3 4.9802783 16 4.9720543 64 4.8998843 256 5.4992213 512 5.5994953 1024 5.93693316 3 5.22165316 16 5.99482116 64 6.64825416 256 7.17682816 512 8.170716 1024 8.65149664 3 7.80153364 16 7.39824864 64 8.39564864 256 17.4949464 512 26.4335464 1024 49.55192256 3 12.36093256 16 20.50781256 64 46.49553256 256 170.5452256 512 333.8809256 1024 675.9459512 3 22.44313512 16 53.82643512 64 164.3493512 256 659.4345512 512 1306.881512 1024 3122.403 lightbgm代码
x_train, x_val, y_train, y_val = train_test_split(X,Y, train_size=0.8)print(f"Number of training examples {len(x_train)}")print(f"Number fo testing examples {len(x_val)}")regressor = lightgbm.LGBMRegressor()regressor.fit(x_train,y_train)train_pred = regressor.predict(x_train)train_rmse = mean_squared_error(train_pred, y_train) ** 0.5print(f"Train RMSE is {train_rmse}")val_pred = regressor.predict(x_val)val_rmse = mean_squared_error(val_pred, y_val)**0.5 print(f"Test RMSE is {val_rmse}")R_squared = r2_score(val_pred,y_val)print('R2',R_squared)结果
Train RMSE is 5385.50, Test RMSE is 1245.1,R2 -2.9991290197894976e+31使用optuna优化的XGBoost代码
def optimize(trial,x,y,regressor): max_depth = trial.suggest_int("max_depth",3,10) n_estimators = trial.suggest_int("n_estimators",5000,10000) max_leaves= trial.suggest_int("max_leaves",1,10) learning_rate = trial.suggest_loguniform('learning_rate', 0.001, 0.1) colsample_bytree = trial.suggest_uniform('colsample_bytree', 0.0, 1.0) min_child_weight = trial.suggest_uniform('min_child_weight',1,3) subsample = trial.suggest_uniform('subsample', 0.5, 1) model = xgb.XGBRegressor( objective ='reg:squarederror', n_estimators=n_estimators, max_depth=max_depth, learning_rate=learning_rate, colsample_bytree=colsample_bytree, min_child_weight=min_child_weight, max_leaves=max_leaves, subsample = subsample) kf=model_selection.KFold(n_splits=5) error=[] for idx in kf.split(X=x , y=y): train_idx , test_idx= idx[0],idx[1] xtrain=x[train_idx] ytrain=y[train_idx] xtest=x[test_idx] ytest=y[test_idx] model.fit(xtrain,ytrain) y_pred = model.predict(xtest) fold_err = metrics.mean_squared_error(ytest,y_pred) error.append(np.sqrt(fold_err)) return np.mean(error) best_params={{'max_depth': 9, 'n_estimators': 9242, 'max_leaves': 7, 'learning_rate': 0.0015809052065858954, 'colsample_bytree': 0.4908644884609704, 'min_child_weight': 2.3502876962874435, 'subsample': 0.5927926099148189}def optimize_xgb(X,y): list_of_y = ["Target 1"] for i,m in zip(range(y.shape[1]),list_of_y): print("{} optimized Parameters on MSE Error".format(m)) optimization_function = partial(optimize , x=X,y=y[:,i],regressor="random_forest") study = optuna.create_study(direction="minimize") study.optimize(optimization_function,n_trials=50)optimize_xgb(X_train, y_train)def modeling(X, y, optimize = "no", max_depth=50, n_estimators=3000, max_leaves=30, learning_rate=0.01, colsample_bytree=1.0, gamma=0.0001, min_child_weight=2, reg_lambda=0.0001): if optimize == "no": model = xgb.XGBRegressor(objective='reg:squarederror') else: model = xgb.XGBRegressor(objective='reg:squarederror', **best_params) if y.shape[1] ==1: model_xgb = model.fit(X, y) cv = RepeatedKFold(n_splits=5, n_repeats=3, random_state=1) scores = [] for i in range(y.shape[1]): scores.append(np.abs(cross_val_score(model, X, y[:,i], scoring='neg_mean_squared_error', cv=cv, n_jobs=-1))) print('Mean MSE of the {} target : {} ({})'.format(i,scores[i].mean(), scores[i].std()) ) return model_xgbmodel_xgb = modeling(X_train,y_train, optimize="yes")model_xgb.fit(X_train, y_train)y_pred = model_xgb.predict(X_test)MSE = mse(y_pred,y_test)RMSE = np.sqrt(MSE)print("TEST MSE",MSE)R_squared = r2_score(y_pred,y_test)print("RMSE: ", np.round(RMSE, 2))print("R-Squared: ", np.round(R_squared, 2))xgboost的结果
TEST MSE 2653915.139388934,RMSE: 1629.08,R-Squared: -1.69回答：
首先，我们必须说，梯度提升模型可以返回训练范围内的和范围外的值。
GB回归器使用前一阶段的残差来拟合树。因此，如果在阶段t的预测值大于目标变量，那么阶段t的残差将是负值，然后阶段t+1的回归树将处理来自之前残差的这些负目标值。
通过逐阶段添加这些得到的树，模型可以预测负值。
处理预测模型中负值的常见技术是对数变换。
目标变量的变换是Y -> log(Y+c)，其中c是常数。人们通常选择类似Y -> log(Y+0.001)或任何其他“非常小”的正数。
